AI Token Counter by Klipto

Estimate how many tokens, words, characters and lines your text uses before you send it to ChatGPT or Claude. Free, in your browser, or count as you paste with Klipto on your Mac.

0
~ Tokens
0
Words
0
Characters
0
Lines

100% in your browser. Nothing is uploaded, logged, or stored.

The count above is characters divided by four. That is the standard shortcut for English prose, and it is a planning figure rather than a billing figure. No real tokenizer runs on this page, and saying so at the top beats letting you find out from an invoice.

Meet Klipto

Count tokens where you write, not in a browser tab.

Klipto is a native macOS clipboard manager. Copy any text and its preview panel shows characters, words, lines and an estimated token count, right where you paste, offline.

See what Klipto does

Why the same text gets different counts

Each model family ships its own tokenizer. GPT-4 uses cl100k_base, a vocabulary of roughly 100k tokens. GPT-4o and the o-series use o200k_base at about 200k, which packs English into fewer pieces. Anthropic does not publish Claude's tokenizer at all, so the only exact source is the API's count_tokens endpoint.

The gaps are wide enough to matter. One Spanish passage cost 30% more tokens under o200k and 56% more under cl100k than its English original. English prose runs near 0.75 words per token. Code drops toward 0.5, and numbers or non-Latin scripts pack denser still.

So read the number above as a range. Four characters per token is close for English prose and loose for code, JSON or Chinese. When a hard context limit or a real bill depends on the figure, call the provider's own tokenizer.

What an estimate is enough for

Two questions, mostly. Will this prompt fit, and roughly what will it cost.

Context ceilings are large in 2026. Claude's Opus class and Sonnet 4.6 reach 1M tokens, GPT-5.5 takes 1M input, Gemini 3.1 Pro handles just over 1M. Advertised ceilings are not working ceilings: independent testing found recall slipping somewhere past 600K to 700K tokens. An estimate tells you whether the prompt fits at all. Whether it fits comfortably is your call.

Cost is the other one. APIs bill per token on input and output both, so a long system prompt or a pasted-in codebase runs the bill up quietly.

On a Mac the same four counts sit under every copy in Klipto's paste preview, which saves the round trip through a browser tab.

Frequently asked questions

How many tokens is 1000 words?

About 1,333 tokens of English prose, at the usual ratio of 100 tokens to 75 words. Going the other way, 1,000 tokens is roughly 750 words. Code and non-English text pack denser.

Is this count exact?

Characters, words and lines are exact. Tokens are an estimate at four characters per token, for every model. For an exact figure use the provider's own tokenizer.

How do I count tokens for Claude?

Through Anthropic's `count_tokens` API endpoint. Claude's tokenizer is not published and there is no library for it, so no offline tool can give you a true Claude count.

Stop re-copying. Download Klipto for Mac.

Local · no card, no account · macOS 14+ · 7.5 MB